INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Canceled

-0.16

arga

-0.14

zh

-0.14

usto

-0.14

uld

-0.14

OK

-0.14

 GÃ¼r

-0.14

 Canc

-0.14

ampa

-0.14

 canceled

-0.14

POSITIVE LOGITS

inson

0.21

 spaces

0.16

 todd

0.15

ieber

0.15

rawn

0.15

 hurricanes

0.14

èķī

0.14

 dias

0.14

bulan

0.14

 trop

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.